Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thy
    -0.07
    _AURA
    -0.07
    _LOCATION
    -0.07
    SO
    -0.07
     vh
    -0.06
    	bar
    -0.06
     बच
    -0.06
    ält
    -0.06
     halinde
    -0.06
    prav
    -0.06
    POSITIVE LOGITS
     tarım
    0.07
     intoler
    0.06
    όν
    0.06
    $file
    0.06
     multer
    0.06
    Players
    0.06
    _masks
    0.06
     weiter
    0.06
     dozens
    0.06
    anean
    0.06
    Act Density 0.006%

    No Known Activations